픽셀 데이터를 이용한 강화 학습 알고리즘 적용에 관한 연구 = A Study on Application of Reinforcement Learning Algorithm Using Pixel Data

다국어 초록 (Multilingual Abstract)

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

목차 (Table of Contents)

• 1. 서 론
• 2. 강화 학습
• 3. 인공 신경망
• 4. Agent 설계
• 5. 학습 프로세스
• 6. 실험 및 결과 분석
• 7. 결 론
• References

참고문헌 (Reference)

1 Sutton, R.S, "Reinforcement Learning : An Introduction" MIT press 1998

2 Christopher J. C. H. Watkins, "Q-learning" Springer Nature 8 (8): 279-292, 1992

3 Sutton, R.S, "Policy Gradient Methods for Reinforcement Learning with Function Approximation" 99 : 1057-1063, 1999

4 Fukushima, K, "Neocognitron : A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position" 34 (34): 193-202, 1980

5 Mnih, V, "Human-level Control Through Deep Reinforcement Learning" 518 (518): 529-533, 2015

6 Bengio, Y, "Greedy Layer-wise Training of Deep Networks" 19 : 153-, 2007

7 Hsu, K, "Artificial Neural Network Modeling of the Rainfall Runoff Process" 31 (31): 2517-2530, 1995